{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7J4X3YRCMD5XL6VEMZ7KNTNS4","short_pith_number":"pith:L7J4X3YR","schema_version":"1.0","canonical_sha256":"5fd3cbef111307dbafd52333f5366d9703651ef387605453fd0f7b08b9b136b0","source":{"kind":"arxiv","id":"2605.06017","version":2},"attestation_state":"computed","paper":{"title":"Matrix-Decoupled Concentration for Autoregressive Sequences: Dimension-Free Guarantees for Sparse Long-Context Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Matrix decoupling of causal dependencies yields dimension-free O(1) variance bounds for sparse rewards in autoregressive sequences.","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Pei-Sen Li","submitted_at":"2026-05-07T11:12:59Z","abstract_excerpt":"Sequence-level evaluations in autoregressive Large Language Models (LLMs) rely on highly dependent token generation. Establishing tight concentration bounds for these processes remains a challenge due to two fundamental bottlenecks in existing frameworks: (i) classical inequalities typically separate dependency structures from target sensitivities, leading to a scalar collapse that inflates the variance proxy to a suboptimal $\\mathcal{O}(N)$ for sparse terminal rewards; (ii) conversely, while certain spatial methods achieve tighter bounds, they lack the strictly causal filtration required by s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.06017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T11:12:59Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"3c943ca4d616f4547e3e7f674fb2b2d2d87fbf47e53ca5cc2ad2ca252ff6a284","abstract_canon_sha256":"a094d5c80fd5286647a73ce97f06c953cf00e0c65e4845ad8f29780b521ab35d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:14.398438Z","signature_b64":"X8WybKab8jBmLJ36C/Bs5Q7kfaw2hzIsh5ixvrLRWn8GjRJjL7RwKy/KDxTNYR2Zl0t4qCRYuFfG8nUoHzSSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fd3cbef111307dbafd52333f5366d9703651ef387605453fd0f7b08b9b136b0","last_reissued_at":"2026-05-20T00:03:14.397270Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:14.397270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matrix-Decoupled Concentration for Autoregressive Sequences: Dimension-Free Guarantees for Sparse Long-Context Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Matrix decoupling of causal dependencies yields dimension-free O(1) variance bounds for sparse rewards in autoregressive sequences.","cross_cats":["math.PR"],"primary_cat":"cs.LG","authors_text":"Pei-Sen Li","submitted_at":"2026-05-07T11:12:59Z","abstract_excerpt":"Sequence-level evaluations in autoregressive Large Language Models (LLMs) rely on highly dependent token generation. Establishing tight concentration bounds for these processes remains a challenge due to two fundamental bottlenecks in existing frameworks: (i) classical inequalities typically separate dependency structures from target sensitivities, leading to a scalar collapse that inflates the variance proxy to a suboptimal $\\mathcal{O}(N)$ for sparse terminal rewards; (ii) conversely, while certain spatial methods achieve tighter bounds, they lack the strictly causal filtration required by s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we establish a sharp McDiarmid-type inequality for dependent sequences, governed strictly by the exact matrix-vector multiplication of the causal dependency resolvent and the target sensitivity vector. This Matrix-Decoupled Concentration (MDC) framework natively recovers optimal constants for Markov chains and exploits directed d-separation to yield order-optimal bounds for causal trees. Crucially, by exactly preserving the coordinate-wise sparsity of rewards within a strictly causal framework, MDC mathematically prevents scalar collapse, guaranteeing a dimension-free O(1) variance proxy","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The process admits a strictly causal filtration whose dependency structure can be represented by a well-defined resolvent matrix that exactly decouples the target sensitivity vector while preserving coordinate-wise sparsity of the reward.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Matrix-Decoupled Concentration achieves dimension-free O(1) variance bounds for sparse rewards in strictly causal autoregressive sequences by decoupling via the exact matrix-vector product of the dependency resolvent and sensitivity vector.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Matrix decoupling of causal dependencies yields dimension-free O(1) variance bounds for sparse rewards in autoregressive sequences.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1ccd6b49ab1f01a6acc238b2471dece2cf0e70f3bef4fabf17f18324ac40db77"},"source":{"id":"2605.06017","kind":"arxiv","version":2},"verdict":{"id":"eebf5833-054d-45b5-8d30-c01ed6847db6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T15:26:29.067015Z","strongest_claim":"we establish a sharp McDiarmid-type inequality for dependent sequences, governed strictly by the exact matrix-vector multiplication of the causal dependency resolvent and the target sensitivity vector. This Matrix-Decoupled Concentration (MDC) framework natively recovers optimal constants for Markov chains and exploits directed d-separation to yield order-optimal bounds for causal trees. Crucially, by exactly preserving the coordinate-wise sparsity of rewards within a strictly causal framework, MDC mathematically prevents scalar collapse, guaranteeing a dimension-free O(1) variance proxy","one_line_summary":"Matrix-Decoupled Concentration achieves dimension-free O(1) variance bounds for sparse rewards in strictly causal autoregressive sequences by decoupling via the exact matrix-vector product of the dependency resolvent and sensitivity vector.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The process admits a strictly causal filtration whose dependency structure can be represented by a well-defined resolvent matrix that exactly decouples the target sensitivity vector while preserving coordinate-wise sparsity of the reward.","pith_extraction_headline":"Matrix decoupling of causal dependencies yields dimension-free O(1) variance bounds for sparse rewards in autoregressive sequences."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06017/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:31:19.185866Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:04:19.359377Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"022b29305ce0177b831f76e52e1947c57d2010d1e7e605dfed21c5849bdf4990"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.06017","created_at":"2026-05-20T00:03:14.397410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.06017v2","created_at":"2026-05-20T00:03:14.397410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06017","created_at":"2026-05-20T00:03:14.397410+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7J4X3YRCMD5","created_at":"2026-05-20T00:03:14.397410+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7J4X3YRCMD5XL6V","created_at":"2026-05-20T00:03:14.397410+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7J4X3YR","created_at":"2026-05-20T00:03:14.397410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4","json":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4.json","graph_json":"https://pith.science/api/pith-number/L7J4X3YRCMD5XL6VEMZ7KNTNS4/graph.json","events_json":"https://pith.science/api/pith-number/L7J4X3YRCMD5XL6VEMZ7KNTNS4/events.json","paper":"https://pith.science/paper/L7J4X3YR"},"agent_actions":{"view_html":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4","download_json":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4.json","view_paper":"https://pith.science/paper/L7J4X3YR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.06017&json=true","fetch_graph":"https://pith.science/api/pith-number/L7J4X3YRCMD5XL6VEMZ7KNTNS4/graph.json","fetch_events":"https://pith.science/api/pith-number/L7J4X3YRCMD5XL6VEMZ7KNTNS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4/action/storage_attestation","attest_author":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4/action/author_attestation","sign_citation":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4/action/citation_signature","submit_replication":"https://pith.science/pith/L7J4X3YRCMD5XL6VEMZ7KNTNS4/action/replication_record"}},"created_at":"2026-05-20T00:03:14.397410+00:00","updated_at":"2026-05-20T00:03:14.397410+00:00"}